Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuations and their frequency in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    long 's' sound

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.46
    只
    -0.35
     Jorg
    -0.33
    ange
    -0.32
    by
    -0.32
     Co
    -0.32
    group
    -0.31
    arg
    -0.31
     Salas
    -0.31
    label
    -0.31
    POSITIVE LOGITS
     ſta
    0.84
    ſelf
    0.84
     myſelf
    0.81
     ſever
    0.80
     ſche
    0.80
     itſelf
    0.79
     faſt
    0.73
     pleaſure
    0.73
     unſ
    0.72
     Reſ
    0.71
    Act Density 0.228%

    No Known Activations